Oil And Gas Communication Data Categorization For Supply Chain Analytics

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The decentralization and disaggregation of communication data from various sources in natural resource production systems, particularly in the oil and gas industry, make it challenging to ascertain meaningful analytics for supply chain functions and finances.

Innovation Solution

Implementing a system that uses a machine learning model for categorizing communication data, leveraging natural language processing to generate embedding data and provide real-time analysis of supply chain functions and finances.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If communication data is collected from multiple decentralized sources, then the quantity and variety of data increases, but the difficulty of analyzing and extracting meaningful analytics increases

Engineering Contradiction:

Improvequantity of communication dataVSAvoiddifficulty of extracting meaningful analytics

Core Design Contradiction:

Quantity of substanceVSDifficulty of detecting and measuring

Solution Approach 1:

The patent segments the communication data into different categories (e.g., supply chain, finance, assets) using machine learning models. This segmentation allows the system to process and analyze large volumes of decentralized data from multiple sources by dividing them into manageable, meaningful categories, thereby reducing the difficulty of extracting analytics while maintaining comprehensive data coverage

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces machine learning models and natural language processing systems as intermediary components between the decentralized data sources and the analysis layer. These intermediaries automatically process, categorize, and prepare the raw communication data, transforming it into structured information that can be easily analyzed, thus bridging the gap between data quantity and analytical capability

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If machine learning models are trained using historical communication data, then the accuracy of categorization improves, but the time required for model training and data processing increases

Engineering Contradiction:

Improveaccuracy of categorizationVSAvoidtime for model training and data processing

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary actions by pre-training machine learning models on historical communication data before they are needed for real-time categorization. This preliminary training phase allows the models to learn patterns and relationships from past data, enabling accurate categorization of new incoming data without requiring time-consuming training during the actual processing operation

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent uses partial action by training models on a representative subset of historical data rather than all available data, and by using pre-computed embeddings from natural language processing. This approach achieves sufficient categorization accuracy while significantly reducing the time and computational resources required for model training and data processing

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS20250378508A1Systems and methods for managing oil and gas production

Publication Date: 2025.12.11 CONOCOPHILLIPS CO

AI summary

Implementations claimed and described herein provide systems and methods for managing natural resource production. The systems and methods use a machine learning model to generate categorizations associated with communication data. The machine learning model is built from historical data.